Efficient VLA Model Inference

VLA: Vision-Language-Action

Follow this topic Ask about this topic

This topic studies how to run vision-language-action models fast enough for responsive, reliable robot control, including on edge devices. Common approaches prune or cache visual tokens, quantize or distill models, reduce action-generation steps, and overlap inference with observation and execution. Methods are tested on manipulation benchmarks such as LIBERO and RoboTwin, as well as real robots, using measures like latency, control frequency, memory, energy, and task success. The main tension is that faster inference can undermine closed-loop reliability or motion quality, so gains must be assessed in full task execution rather than by model speed alone.

Latest papers

190 papers56 papers in the last four weeks, up 115% on the four weeks before. 0.3% of all new papers.

Apr 7, 2026

VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success

Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action decision-making for cross-modal semantic alignment, exhibiting broad application potential. However, the joint processing of high-dimensional visual features, complex linguistic inputs, and continuous action sequences incurs significant computational overhead and low inference efficiency, thereby hindering real-time deployment and reliability. To address this issue, we use image entropy to quantify the grayscale distribution characteristics of each visual token and introduce attention entropy to capture the distribution of attention scores over task-related text. Visual entropy identifies texture-rich or structurally informative regions, while attention entropy pinpoints semantically relevant tokens. Combined with timestep information, these metrics enable a dynamic transition strategy that shifts the model's focus from global visual features to attention-guided local informative regions. Thus, the resulting VLA-InfoEntropy method integrates spatial, semantic, and temporal cues to reduce redundancy while preserving critical content. Extensive experiments show that our method reduces inference parameters, accelerates inference speed, and outperforms existing approaches.

Chuhang Liu, Yayun He, Zuheng Kang +2

Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China · Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China

Efficient VLA Model Inference Vision-Language-Action Models Visual Token Pruning

Apr 3, 2026

Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA

Vision-Language-Action (VLA) models, as large foundation models for embodied control, have shown strong performance in manipulation tasks. However, their performance comes at high inference cost. To improve efficiency, recent methods adopt action chunking, which predicts a sequence of future actions for open-loop execution. Although effective for reducing computation, open-loop execution is sensitive to environmental changes and prone to error accumulation due to the lack of close-loop feedback. To address this limitation, we propose Speculative Verification for VLA Control (SV-VLA), a framework that combines efficient open-loop long-horizon planning with lightweight closed-loop online verification. Specifically, SV-VLA uses a heavy VLA as a low-frequency macro-planner to generate an action chunk together with a planning context, while a lightweight verifier continuously monitors execution based on the latest observations. Conditioned on both the current observation and the planning context, the verifier compares the planned action against a closed-loop reference action and triggers replanning only when necessary. Experiments demonstrate that SV-VLA combines the efficiency of chunked prediction with the robustness of closed-loop control, enabling efficient and reliable VLA-based control in dynamic environments. Code is available: https://github.com/edsad122/SV-VLA.

Zihua Wang, Zhitao Lin, Ruibo Li +4

School of Computer Science and Engineering, Southeast University, Nanjing, China · Nanyang Technological University, Singapore · School of Cyber Science and Engineering, Southeast University, Nanjing, China +1

Closed-Loop Control of VLA Models Vision-Language-Action Models Efficient VLA Model Inference Robustness of VLA Models

Apr 2, 2026

MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation

A central challenge in mobile manipulation is preserving multiple plausible action modes while remaining reactive during execution. For example, grasping a bottle in a cluttered scene can be achieved through multiple physically feasible base-arm motion plans. Deterministic VLA policies trained with

L_1

regression are efficient, but they tend to average across valid modes and may produce physically invalid actions. Diffusion-based generative policies can better represent multimodal action distributions, yet their proposals may be weakly constrained when generated from pure noise, and iterative sampling can increase inference cost. Action chunking helps amortize inference, but it also introduces partially open-loop execution, allowing small mismatches to accumulate into drift. We present MobiGuide, a generative VLA model for efficient mobile manipulation, where action generation is guided by a structured trajectory vocabulary. Constructed from expert demonstrations, this vocabulary encodes plausible whole-body motion patterns and provides structured priors for feasible action generation. Given the current observation and instruction, MobiGuide locally refines these reference trajectories into context-compatible action proposals and selects the most suitable trajectory for execution. This preserves multimodal action candidates while keeping generation constrained around feasible expert-like motion modes. To mitigate chunk-induced drift, we further introduce a lightweight residual correction module that performs high-frequency, per-step adjustments during rollout. Across diverse mobile manipulation tasks, MobiGuide improves success and stability under execution disturbances while maintaining low-latency inference.

Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3

UQMM Lab, The University of Queensland, Brisbane, Australia · Robotics and Autonomous Systems Group, CSIRO, Brisbane, Australia

Mobile Manipulation Diffusion Policy Efficient VLA Model Inference Robustness of VLA Models

Mar 30, 2026

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for resource-constrained edge platforms in real-world deployments. However, since different stages of VLA (observation, action generation and execution) must proceed sequentially, and wait for the completion of the preceding stage, the system suffers from frequent halting and high latency. To address this, We conduct a systematic analysis to identify the challenges for fast and fluent generation, and propose enabling VLAs with the ability to asynchronously parallelize across VLA stages in a "streaming" manner. First, we eliminate the reliance on action chunking and adopt action flow matching, which learns the trajectory of action flows rather than denoising chunk-wise actions. It overlaps the latency of action generation and execution. Second, we design an action saliency-aware adaptive observation mechanism, thereby overlapping the latency of execution and observation. Without sacrificing performance, StreamingVLA achieves substantial speedup and improves the fluency of execution. It achieves a 2.4

\times

latency speedup and reduces execution halting by 6.5

\times

.

Yiran Shi, Dongqi Guo, Tianchen Zhao +8

Tsinghua University · Lenovo Group Ltd.

Vision-Language-Action Models Efficient VLA Model Inference

Mar 27, 2026

Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate

In deployment of the VLA models to real-world robotic tasks, execution speed matters. In previous work arXiv:2510.26742 we analyze how to make neural computation of VLAs on GPU fast. However, we leave the question of how to actually deploy the VLA system on the real robots open. In this report we describe a set of practical techniques to achieve the end-to-end result of running a VLA-driven robot at an impressive speed in real world tasks that require both accuracy and dexterity. The stack of technology ranges across calibration, planning & control, and learning based method to identify optimal execution speed. In the tasks we show, the robot even executes in a speed on par with casual human operation and approaching the hardware limit of our lightweight arm. The unaccelerated videos and inference traces are provided in https://dexmal.github.io/realtime-vla-v2/.

Chen Yang, Yucheng Hu, Yunchao Ma +3

Dexmal

Robotic Control VLMs for Robotics Efficient VLA Model Inference

Mar 26, 2026

Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models

Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction methods predominantly rely on attention magnitude as a static selection. In this work, we challenge this assumption, revealing that high-attention tokens are task-dependent and can even degrade policy performance. To address this, we introduce TIES (Tau-guided Inter-layer Efficient Selection), a dynamic framework guided by inter-layer token ranking consistency. By adaptively balancing attention magnitude with ranking consistency, TIES ensures robust token selection without requiring additional training. On the CogACT + SIMPLER benchmark, TIES improves average success rates by 6% while reducing token usage by 78%, and demonstrate strong generalization across diverse decoders and benchmarks.

Peiju Liu, Jinming Liu, Xipeng Qiu +1

Fudan University

Efficient VLA Model Inference Vision-Language-Action Models Visual Token Pruning

Mar 24, 2026

Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation

Efficient visual representation is a central image-processing challenge in embodied manipulation, where policies repeatedly process dense visual-token sequences during closed-loop control. Existing methods rank or prune tokens using semantic relevance, VLM attention, cross-frame redundancy, or motion in the action space. These signals may discard task-relevant regions when instruction-related appearance and observed image motion are not yet spatially aligned. We introduce Interaction-Aligned Pruning (IAprune), a training-free method that treats per-frame budget setting and within-budget token selection as two linked decisions. Semantic--motion spatial agreement guides the choice between Conservative and Aggressive coverage, and the resulting region size is mapped to a calibrated dynamic budget. Continuous semantic and motion responses rank the existing tokens, while geometric residual correction redirects fixed selection slots toward under-represented boundaries without increasing the sequence length. Across four embodied manipulation policies, three simulation benchmarks, and a real-robot platform, IAprune provides a favorable accuracy--efficiency trade-off, matching the unpruned policy on LIBERO with a

1.54\times

speedup and reaching

1.48\times

acceleration on a real robot. Phase-wise analysis shows that retention gains are largest under tight budgets early in an episode, while fixed-budget analysis confirms that geometry replaces low-priority tokens with boundary and contact-region evidence rather than retaining more tokens. Our project website is: IAprune.com.

Jintao Cheng, Weibin Li, Haozhe Wang +7

Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China · University of Macau, Macau, China · School of Data Science and Engineering, Xingzhi College, South China Normal University, Guangzhou, China +3

Visual Token Pruning Efficient VLA Model Inference Robotic Manipulation

Mar 24, 2026

Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring

Deploying Vision-Language-Action (VLA) models on resource-constrained edge platforms encounters a fundamental conflict between high-latency semantic inference and the high-frequency control required for dynamic manipulation. To address the challenge, this paper presents Agile-VLA, a hierarchical framework designed for industrial pose reorientation tasks on edge devices such as the NVIDIA Jetson Orin Nano. The core innovation is an Implicit Affordance Anchoring mechanism that directly maps geometric visual cues, specifically centroid and rim keypoint anchors, into structured parametric action primitives, thereby substantially reducing reliance on high-latency semantic inference during closed-loop control. By decoupling perception (10 Hz) from control (50 Hz) via an asynchronous dual-stream architecture, the system effectively mitigates the frequency mismatch inherent in edge-based robot learning. Experimental results on a standard 6-DoF manipulator demonstrate that Agile-VLA achieves robust rectification of complex, irregular workpieces using only 5-shot demonstrations through extrinsic dexterity.

Teng Yan, Zhengyang Pei, Chengyu Shi +8

The Hong Kong University of Science and Technology (Guangzhou)

Affordance-Based Robotic Manipulation Robotic Manipulation Vision-Based Robot Control Efficient VLA Model Inference Data-Efficient Robot Learning

Mar 23, 2026

DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical planning, as well as precise manipulations demanding fine-grained spatial perception. Recent efforts have incorporated Chain-of-Thought (CoT) reasoning to endow VLA models with a ``thinking before acting'' capability. However, current CoT-based VLA models face two critical limitations: 1) an inability to simultaneously capture low-level visual details and high-level logical planning due to their reliance on isolated, single-modal CoT; 2) high inference latency with compounding errors caused by step-by-step autoregressive decoding. To address these limitations, we propose DualCoT-VLA, a visual-linguistic CoT method for VLA models with a parallel reasoning mechanism. To achieve comprehensive multi-modal reasoning, our method integrates a visual CoT for low-level spatial understanding and a linguistic CoT for high-level task planning. Furthermore, to overcome the latency bottleneck, we introduce a parallel CoT mechanism that incorporates two sets of learnable query tokens, shifting autoregressive reasoning to single-step forward reasoning. Extensive experiments demonstrate that our DualCoT-VLA achieves state-of-the-art performance on the LIBERO and RoboCasa GR1 benchmarks, as well as in real-world platforms.

Zhide Zhong, Junfeng Li, Junjie He +10

The Hong Kong University of Science and Technology (Guangzhou) · Huawei Foundation Model Department

VLMs for Robotics Reasoning for VLA Models Efficient VLA Model Inference

Mar 21, 2026

RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models

Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an effective fix by easing edge-device computing pressure to meet real-time needs. However, existing ECC frameworks are suboptimal for VLA models due to two challenges: (1) Diverse model structures hinder optimal ECC segmentation point identification; (2) Even if the optimal split point is determined, changes in network bandwidth can cause performance drift. To address these issues, we propose a novel ECC deployment framework for various VLA models, termed RoboECC. Specifically, we propose a model-hardware co-aware segmentation strategy to help find the optimal segmentation point for various VLA models. Moreover, we propose a network-aware deployment adjustment approach to adapt to the network fluctuations for maintaining optimal performance. Experiments demonstrate that RoboECC achieves a speedup of up to 3.28x with only 2.55%~2.62% overhead.

Zihao Zheng, Hangyu Cao, Jiayu Chen +6

School of Computer Science, Peking University, Beijing, China · School of Computer Science, South China University of Technology, Guangzhou, China · School of Artificial Intelligence, Beijing Normal University, Beijing, China +1

Edge-Cloud Collaborative Inference Efficient VLA Model Inference Edge-Cloud Computing Edge Computing Distributed Inference VLMs for Robotics

Mar 19, 2026

FASTER: Rethinking Real-Time Flow VLAs

Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in

π_{0.5}

and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks substantially improved real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.

Yuxiang Lu, Zhe Liu, Xianzhe Fan +5

The University of Hong Kong · ACE Robotics

Efficient VLA Model Inference Robotics Action Chunking

Mar 19, 2026

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of ``efficiency'' in current VLA research, characterized by parameters, FLOPs, or token decoding throughput, does not reflect actual performance on robotic platforms. In real-world execution, efficiency is determined by system-level embodied behaviors such as task completion time, trajectory smoothness, cumulative joint rotation, and motion energy. Through controlled studies across model compression, token sparsification, and action sequence compression, we make several observations that challenge common assumptions. (1) Methods that reduce computation under conventional metrics often increase end-to-end execution cost or degrade motion quality, despite maintaining task success rates. (2) System-level embodied efficiency metrics reveal performance differences in the learned action policies that remain hidden under conventional evaluations. (3) Common adaptation methods such as in-context prompting or supervised fine-tuning show only mild and metric-specific improvements in embodied efficiency. While these methods can reduce targeted embodied-efficiency metrics such as jerk or action rate, the resulting gains may come with trade-offs in other metrics, such as longer completion time. Taken together, our results suggest that conventional inference efficiency metrics can overlook important aspects of embodied execution. Incorporating embodied efficiency provides a more complete view of policy behavior and practical performance, enabling fairer and more comprehensive comparisons of VLA models.

Zhuofan Li, Hongkun Yang, Zhenyang Chen +4

Celine · Hong Kong University of Science and Technology · Georgia Institute of Technology

Efficient VLA Models Vision-Language-Action Models Efficient VLA Model Inference Robotics

Mar 18, 2026

ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models

Vision-Language-Action (VLA) policies increasingly use Flow Matching (FM) action heads to generate action chunks as continuous trajectories. At inference, an FM head solves an ordinary differential equation (ODE): starting from a prior action latent, it repeatedly queries a learned velocity field to advance the state toward the decoded action chunk. Because each query depends on the preceding state, this iterative decoding can impose substantial sequential action-head cost at deployment. We propose ProbeFlow, a training-free framework that routes each action chunk to an integration schedule using a Lookahead Consistency Probe. Optional oscillation-conditioned (OSC) threshold adaptation reuses the same velocity evaluations and can trade part of the acceleration for potentially better task performance. On MetaWorld, the fixed-threshold configuration uses 2.60 scheduled steps (2.92 action-head evaluations) and reports 15.9 ms action-head latency, versus 235.7 ms for 50-step Euler, while obtaining 83.2% success versus 82.5%. On LIBERO, it uses 4.53 scheduled steps (5.09 action-head evaluations), reports 32.7 ms, and obtains 88.7% success, compared with 278.7 ms and 92.5% for 50-step Euler. We also evaluate OSC on three real-world manipulation tasks with 50 trials per method and task. These evaluations characterize action-decoding compute-performance trade-offs without additional training.

Zhou Fang, Jiaqi Wang, Wenzhuo Li +2

School of Computer Science and Engineering, Southeast University, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China · School of Electronic Science & Engineering, Southeast University, China

Efficient VLA Model Inference Vision-Language-Action Models Flow Matching

Mar 18, 2026

HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising acceleration method which can be divided into two categories: drafter-based SD and retrieval-based SD. Each of the two methods demonstrates complementary advantages and limitations when applied to VLA models, leading to the hypothesis that a hybrid approach integrating these two methods will yield better performance. In this paper, we first conduct a series of detailed analyses to reveal the advantages and feasibility of hybrid utilization. However, even with the aforementioned key insights, implementing hybrid SD in VLA models presents several challenges: (1) draft rejection and persistent errors in retrieval-based SD; (2) difficulty in determining the hybrid boundary. To address these, we propose the HeiSD framework. We propose a retrieval-based SD optimization method in HeiSD, which contains a verify-skip mechanism and a sequence-wise relaxed acceptance strategy. Moreover, we proposed a kinematic-based fused metric in HeiSD to automatically determine the hybrid boundary. Experimental results demonstrate that HeiSD attains a speedup of up to 2.45x in simulation benchmarks and 2.06x~2.41x in real-world scenarios, while sustaining a high task success rate.

Zihao Zheng, Zhihao Mao, Sicheng Tian +8

School of Computer Science, Peking University · School of Computer Science, China University of Geosciences (Wuhan) · School of Artificial Intelligence, Beijing Normal University +1

Efficient VLA Model Inference Speculative Decoding Vision-Language-Action Models

Mar 16, 2026

Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.

Utkarsh Grover, Ravi Ranjan, Mingyang Mao +9

University of South Florida, USA · Florida International University, USA · Johns Hopkins University, USA +2

Robot Foundation Models Edge Computing Efficient VLA Model Inference

Mar 16, 2026

AnolisVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation

In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based on visual observations and natural language instructions. This task is essential for service robots that operate in human environments, and requires safety, efficiency, and task-level generality. Although Vision-Language-Action models (VLAs) have demonstrated strong performance for this task, their deployment in resource-constrained environments remains challenging because of the computational cost of standard transformer backbones. To overcome this limitation, we propose AnolisVLA, a lightweight VLA that uses a deep state space model to process multimodal sequences efficiently. The model uses lightweight, fast sequential state modeling to process visual and textual inputs. This design enables efficient trajectory generation. We evaluated the proposed method in simulation and on two real robot platforms. Compared with SmolVLA at a comparable parameter scale, AnolisVLA achieved higher task success rates, faster inference, and comparable GPU memory usage. In mobile manipulation, it outperformed the larger, 3-billion-parameter

π_{0.5}

model by 21 percentage points in task success rate while achieving approximately three times faster inference.

Yusuke Takagi, Motonari Kambara, Daichi Yashima +3

Keio University, 3-14-1 Hiyoshi, Kohoku, Yokohama, Kanagawa 223-8522, Japan.

Language-Conditioned Robot Manipulation Vision-Language-Action Models Efficient VLA Model Inference Mobile Manipulation

Mar 16, 2026

AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either struggle to resolve distribution misalignment between reasoning and action spaces, underexploit the general reasoning capabilities of pretrained VLMs, or incur substantial inference latency during action policy generation, which degrades driving performance. To address these challenges, we propose AutoMoT in this work, an end-to-end AD framework that unifies reasoning and action generation within a single vision-language-action (VLA) model. Our approach leverages a mixture-of-transformer (MoT) architecture with joint attention sharing, which preserves the general reasoning capabilities of pre-trained VLMs while enabling efficient fast-slow inference through asynchronous execution at different task frequencies. Extensive experiments on multiple benchmarks, under both open- and closed-loop settings, demonstrate that AutoMoT achieves competitive performance compared to state-of-the-art methods. We further investigate the functional boundary of pre-trained VLMs in AD, examining when AD-tailored fine-tuning is necessary. Our results show that pre-trained VLMs can achieve competitive multi-task scene understanding performance through semantic prompting alone, while fine-tuning remains essential for action-level tasks such as decision-making and trajectory planning. We refer to https://automot-website.github.io/ for the demonstration videos and qualitative results.

Wenhui Huang, Songyan Zhang, Qihang Huang +6

Nanyang Technological University, Singapore · Harvard University, US · Xiaomi EV, China

Mixture-of-Transformers End-to-End Autonomous Driving Vision-Language-Action Models VLMs for Autonomous Driving Efficient VLA Model Inference Reasoning for VLA Models

Mar 15, 2026

OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observations under distinct time constraints. Recent Mixture-of-Transformers (MoT) Vision-Language-Action Models (VLAs) support such heterogeneous outputs, yet existing inference systems incur redundant computation and resource contention when serving concurrent tasks on-device. We identify isolated KV cache management as the root cause. To address this, we propose unified KV cache management, an inference design that treats the KV cache as a first-class shared resource across tasks and control cycles. This abstraction enables two key optimizations: cross-task KV sharing eliminates redundant prefill of shared observations, while cross-frame continuous batching batches unfinished language requests from different frames and advances them within a per-frame decoding budget. We implement this design in OxyGen and evaluate

π_{0.5}

on NVIDIA GeForce RTX 4090 and Jetson AGX Thor. OxyGen achieves up to 3.7

\times

speedup over isolated execution, delivering over 200 tokens/s language throughput and 70 Hz action frequency simultaneously on RTX 4090. We also validate the design on Xiaomi-Robotics-0 and StarVLA across different backbones and expert configurations. We further demonstrate the inference gains on a humanoid robot with on-board Jetson AGX Thor.

Xiangyu Li, Huaizhi Tang, Xin Ding +3

Institute for AI Industry Research (AIR), Tsinghua University · Department of Electronic Engineering, Tsinghua University · University of Science and Technology of China

Efficient VLA Model Inference KV-Cache Management On-Device Inference

Mar 11, 2026

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

We propose DynVLA, a driving VLA model that introduces a new CoT paradigm termed Dynamics CoT. DynVLA forecasts compact world dynamics before action generation, enabling more informed and physically grounded decision-making. To obtain compact dynamics representations, DynVLA introduces a Dynamics Tokenizer that compresses future evolution into a small set of dynamics tokens. Considering the rich environment dynamics in interaction-intensive driving scenarios, DynVLA decouples ego-centric and environment-centric dynamics, yielding more accurate world dynamics modeling. We then train DynVLA to generate dynamics tokens before actions through SFT and RFT, improving decision quality while maintaining latency-efficient inference. Compared to Textual CoT, which lacks fine-grained spatiotemporal understanding, and Visual CoT, which introduces substantial redundancy due to dense image prediction, Dynamics CoT captures the evolution of the world in a compact, interpretable, and efficient form. Extensive experiments on NAVSIM, Bench2Drive, and a large-scale in-house dataset demonstrate that DynVLA consistently outperforms Textual CoT and Visual CoT methods, validating the effectiveness and practical value of Dynamics CoT. Project Page: https://yaoyao-jpg.github.io/dynvla.

Shuyao Shang, Bing Zhan, Yunfei Yan +9

NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA) · Yinwang Intelligent Technology Co. Ltd.

Autonomous Driving Vision-Language-Action Models Reasoning for VLA Models World Models for Autonomous Driving World Models Efficient VLA Model Inference

Mar 11, 2026

DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either prune or merge tokens uniformly, degrading the spatial reasoning essential for robotic control. We present DepthCache, a training-free framework that leverages depth as a structural prior for visual token compression. It partitions observations into depth-based regions and applies spatially differentiated merge ratios, preserving the near-field workspace while compressing the distant background. To exploit temporal redundancy, DepthCache distributes the merging process across consecutive frames, ensuring consistent representations while reducing per-step computation. A motion-adaptive pipeline further optimizes auxiliary view compression based on end-effector dynamics. The framework requires no model modification, generalizing across diverse VLA architectures. On the LIBERO benchmark, DepthCache achieves up to 1.28x inference speedup with less than 1% average success rate degradation across three VLA models (pi_0.5, OpenVLA, GR00T), whereas pruning and merging baselines incur 4--24% degradation at comparable compression. Real-world experiments on a physical manipulator demonstrate that DepthCache enables faster task throughput and more responsive closed-loop control in latency-sensitive scenarios.

Yuquan Li, Lianjie Ma, Han Ding +1

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China. · School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China.

Efficient VLA Model Inference Visual Token Compression Vision-Language-Action Models Visual Token Merging VLMs for Robotics

Mar 9, 2026

ActECC: Action Chunk Temporal Harnessing for Edge-Cloud Collaborative VLA Inference System

VLA models have emerged as the mainstream for embodied intelligence, which decouples reasoning and execution via action chunks. To enable real-time deployment of VLA models, existing studies investigate edge-cloud collaborative inference, which pose two challenges to the action chunk mechanism. (1) Edge-cloud collaboration complicates system latency components, hindering the determination of valid ranges for action chunks. (2) Latency fluctuations in cross-edge update links under edge-cloud scenarios make it difficult to schedule replanning requests. To address these, we analyze the key factors affecting action chunk usable ranges and replanning request timing, revealing phase dependence and edge-cloud latency constraints. Based on these insights, we propose ActECC, which enables Action Chunk Temporal Harnessing through kinematics-guided usable range assessment and delay-aware replanning scheduling. Experiments show that ActECC reduces per-action latency by up to 27.4% and cloud calls by up to 45.1%, while lowering average execution error compared with existing edge-cloud collaborative.

Zihao Zheng, Zhihao Mao, Hui Huang +9

School of Computer Science, Peking University, Beijing, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China.

Temporal Modeling for VLA Models Edge-Cloud Collaborative Inference Efficient VLA Model Inference

Mar 9, 2026

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Existing VLA quantization methods mainly trade off inference speed and model performance while rarely investigating how quantization alters runtime errors. By comparing error distributions between full-precision and quantized models, we identify distinct evolutionary patterns for the two types of errors: quantization enlarges the variance of translation error distributions and increases their dispersion, whereas the distribution center of rotation errors gradually shifts across execution steps, demonstrating cumulative drift. Motivated by this observation, we rethink the optimal quantization strategy for VLA models and propose DyQ-VLA, a runtime-error-aware quantization framework, which dynamically selects activation precision according to execution steps and tracks as well as compensates rotation errors via accumulated quantization residuals. Corresponding operators and runtime adaptation strategies are devised within the framework to enable dynamic-precision execution. Experiments show that DyQ-VLA achieves a 1.88 to 1.93 inference speedups while maintaining comparable or higher average task success rates. Moreover, it reduces mean execution steps by 17.7% to 19.8%. Our code is here: https://anonymous.4open.science/r/DyQ-VLA-7F51/.

Zihao Zheng, Hangyu Cao, Chibang Tao +9

School of Computer Science, Peking University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. +1

VLM Quantization Efficient VLA Model Inference Efficient VLA Models Activation Quantization Vision-Language-Action Models Neural Network Quantization

Mar 5, 2026

Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation

Balancing high-level semantic reasoning with low-level reactive control remains a core challenge in visual robotic manipulation. While Vision-Language Models (VLMs) excel at cognitive planning, their inference latency precludes real-time execution. Conversely, fast Vision-Language-Action (VLA) models often lack the semantic depth required for complex, long-horizon tasks. To bridge this gap, we introduce Critic in the Loop, an adaptive hierarchical framework driven by dynamic VLM-Expert scheduling. At its core is a bionic Tri-System architecture comprising a VLM brain for global reasoning, a VLA cerebellum for reactive execution, and a lightweight visual Critic. By continuously monitoring the workspace, the Critic dynamically routes control authority. It sustains rapid closed-loop execution via the VLA for routine subtasks, and adaptively triggers the VLM for replanning upon detecting execution anomalies such as task stagnation or failures. Furthermore, our architecture seamlessly integrates human-inspired rules to intuitively break infinite retry loops. This visually-grounded scheduling minimizes expensive VLM queries, while substantially enhancing system robustness and autonomy in out-of-distribution (OOD) scenarios. Comprehensive experiments on challenging, long-horizon manipulation benchmarks reveal that our approach achieves state-of-the-art performance.

Pengfei Yi, Yingjie Ma, Wenjiang Xu +4

Institute of Automation, Chinese Academy of Sciences · the School of Artificial Intelligence, University of Chinese Academy of Sciences

Long-Horizon Robotic Manipulation VLMs for Robotics Robustness of VLA Models Adaptive Model Routing Efficient VLA Model Inference

Mar 3, 2026

LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics

Vision-Language-Action (VLA) models provide a unified framework for perception, language conditioning, and action generation, but many existing systems remain difficult to deploy in embedded robotic settings because of their computational requirements and inference latency. In this paper, we present LiteVLA-Edge, a deployment-oriented VLA pipeline for fully on-device inference on Jetson Orin-class hardware. Our approach combines supervised image-to-action fine-tuning in FP32 with post-training 4-bit GGUF quantization and GPU-accelerated inference through the llama.cpp runtime. Under our deployment configuration, LiteVLA-Edge achieves a mean end-to-end latency of 150.5,ms (approximately 6.6,Hz) while operating entirely offline within a ROS~2-integrated perception--reasoning--action pipeline. Rather than introducing a new policy objective, our contribution is a practical systems path for executing compact multimodal control models locally on embedded hardware while preserving modular interfaces between perception, reasoning, and actuation. These results establish timing feasibility for reactive language-conditioned control and provide a reproducible baseline for future task-level evaluation of on-device VLAs in robotics.

Justin Williams, Kishor Datta Gupta, Roy George +1

Clark Atlanta University, Atlanta, GA, USA · Siemens Corporation, Princeton, NJ, USA

Efficient VLA Model Inference On-Device Inference VLMs for Robotics

Mar 2, 2026

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization strategy that can boost inference speed. Two key issues emerge when integrating VLA and SD: first, SD relies on re-inference to address token errors, which is computationally expensive; second, to mitigate token errors, the acceptance threshold in SD requires careful adjustment. Existing works fail to address the above two issues effectively. Meanwhile, as the bridge between AI and the physical world, existing embodied intelligence has overlooked the application of robotic kinematics. To address these issues, we innovatively combine token-domain VLA models with kinematic-domain prediction for SD, proposing a kinematic-rectified SD framework named KERV. We employ a kinematics-based Kalman Filter to predict actions and compensate for SD errors, avoiding costly re-inference. Moreover, we design a kinematics-based adjustment strategy to dynamically rectify the acceptance threshold, addressing the difficulty of threshold determination. Experimental results across diverse tasks and environments demonstrate that KERV achieves 27%~37% acceleration with nearly no Success Rate loss.

Zihao Zheng, Zhihao Mao, Maoliang Li +6

School of Computer Science, Peking University, Beijing, China · School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China

Robot Kinematics Efficient VLA Model Inference Vision-Language-Action Models Robotics

Mar 2, 2026

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction and execution, recent work has attempted to further improve performance by introducing explicit reasoning during inference. However, such approaches face significant limitations. They often depend on data-intensive resources such as Chain-of-Thought (CoT) style annotations to decompose tasks into step-by-step reasoning, and in many cases require additional visual grounding annotations (e.g., bounding boxes or masks) to highlight relevant image regions. Moreover, they involve time-consuming dataset construction, labeling, and retraining, which ultimately results in longer inference sequences and reduced efficiency. To address these challenges, we propose ATA, a novel training-free framework that introduces implicit reasoning into VLA inference through complementary attention-guided and action-guided strategies. Unlike CoT or explicit visual-grounding methods, ATA formulates reasoning implicitly by integrating attention maps with an action-based region of interest (RoI), thereby adaptively refining visual inputs without requiring extra training or annotations. ATA is a plug-and-play implicit reasoning approach for VLA models, lightweight yet effective. Extensive experiments show that it consistently improves task success and robustness while preserving, and even enhancing, inference efficiency.

Cheng Yang, Jianhao Jiao, Lingyi Huang +8

Rutgers University · University College London · Rice University +1

Vision-Language-Action Models Reasoning for VLA Models Efficient VLA Model Inference Robustness of VLA Models

Mar 2, 2026

Mean-Flow based One-Step Vision-Language-Action

Recent advances in FlowMatching-based Vision-Language-Action (VLA) frameworks have demonstrated remarkable advantages in generating high-frequency action chunks, particularly for highly dexterous robotic manipulation tasks. Despite these notable achievements, their practical applications are constrained by prolonged generation latency, which stems from inherent iterative sampling requirements and architectural limitations. To address this critical bottleneck, we propose a Mean-Flow based One-Step VLA approach. Specifically, we resolve the noise-induced issues in the action generation process, thereby eliminating the consistency constraints inherent to conventional Flow-Matching methods. This significantly enhances generation efficiency and enables one-step action generation. Real-world robotic experiments show that the generation speed of the proposed Mean-Flow based One-Step VLA is 8.7 times and 83.9 times faster than that of SmolVLA and Diffusion Policy, respectively. These results elucidate its great potential as a high-efficiency backbone for VLA-based robotic manipulation.

Yang Chen, Xiaoguang Ma, Bin Zhao

Efficient VLA Model Inference Vision-Language-Action Models Robotic Manipulation Mean Flow

Mar 2, 2026

Unifying Language-Action Understanding and Generation for Autonomous Driving

Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer from two critical limitations: a persistent misalignment between language instructions and action outputs, and the inherent inefficiency of typical auto-regressive action generation. In this paper, we introduce LinkVLA, a novel architecture that directly addresses these challenges to enhance both alignment and efficiency. First, we establish a structural link by unifying language and action tokens into a shared discrete codebook, processed within a single multi-modal model. This structurally enforces cross-modal consistency from the ground up. Second, to create a deep semantic link, we introduce an auxiliary action understanding objective that trains the model to generate descriptive captions from trajectories, fostering a bidirectional language-action mapping. Finally, we replace the slow, step-by-step generation with a two-step coarse-to-fine generation method C2F that efficiently decodes the action sequence, saving 86% inference time. Experiments on closed-loop driving benchmarks show consistent gains in instruction following accuracy and driving performance, alongside reduced inference latency.

Xinyang Wang, Qian Liu, Wenjie Ding +7

State Key Lab of CAD&CG, Zhejiang University · Li Auto

Vision-Language-Action Models End-to-End Autonomous Driving Efficient VLA Model Inference

Mar 1, 2026

Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures

Vision-Language-Action (VLA) models are an emerging class of workloads critical for robotics and embodied AI at the edge. As these models scale, they demonstrate significant capability gains, yet they must be deployed locally to meet the strict latency requirements of real-time applications. This paper characterizes VLA performance on two generations of edge hardware, viz. the Nvidia Jetson Orin and Thor platforms. Using MolmoAct-7B, a state-of-the-art VLA model, we identify a primary execution bottleneck: up to 75% of end-to-end latency is consumed by the memory-bound action-generation phase. Through analytical modeling and simulations, we project the hardware requirements for scaling to 100B parameter models. We also explore the impact of high-bandwidth memory technologies and processing-in-memory (PIM) as promising future pathways in edge systems for embodied AI.

Manoj Vishwanathan, Suvinay Subramanian, Anand Raghunathan

Google, Mountain View, CA USA · Purdue University, West Lafayette, IN USA

Vision-Language-Action Models Efficient VLA Model Inference AI Accelerator Inference Edge Computing

Feb 26, 2026

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation

Vision-Language-Action (VLA) models have shown remarkable success in robotic tasks like manipulation by fusing a language model's reasoning with a vision model's 3D understanding. However, their high computational cost remains a major obstacle for real-world applications that require real-time performance. We observe that the actions within a task have varying levels of importance: critical steps demand high precision, while less important ones can tolerate more variance. Leveraging this insight, we propose DySL-VLA, a novel framework that addresses computational cost by dynamically skipping VLA layers based on each action's importance. DySL-VLA categorizes its layers into two types: informative layers, which are consistently executed, and incremental layers, which can be selectively skipped. To intelligently skip layers without sacrificing accuracy, we invent a prior-post skipping guidance mechanism to determine when to initiate layer-skipping. We also propose a skip-aware two-stage knowledge distillation algorithm to efficiently train a standard VLA into a DySL-VLA. Our experiments indicate that DySL-VLA achieves 2.1% improvement in success length over Deer-VLA on the Calvin dataset, while simultaneously reducing trainable parameters by a factor of 85.7 and providing a 3.75x speedup relative to the RoboFlamingo baseline at iso-accuracy. Our code is available on https://github.com/PKU-SEC-Lab/DYSL_VLA.

Zebin Yang, Yijiahao Qi, Tong Xie +3

Institute for Artificial Intelligence, Peking University, Beijing, China · School of Integrated Circuits, Peking University, Beijing, China · School of Electronics Engineering and Computer Science, Peking University, Beijing, China +2

Layer Skipping in Language Model Decoding Efficient VLA Model Inference Vision-Language-Action Models Robotic Manipulation